competitor-monitor

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (Process step 2) explicitly fetches and ingests public third-party content — e.g., competitor websites, social media profiles (LinkedIn, X, Facebook, Instagram, YouTube) and public ad libraries (Google Ads Transparency Center, Meta Ad Library) — which the agent reads and uses to set baselines, alerts, and monitoring actions, exposing it to untrusted user-generated content that could carry indirect prompt injection.